InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write.

Jesse Berent

Blagoj Mitrevski Arina Rak Julian Schnitzler Chengkun Li Andrii Maksai Jesse Berent Claudiu Cristian Musat InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=pSyUfV5BqA db/journals/tmlr/tmlr2025.html#MitrevskiRSLMBM25

Riccardo Brioschi Aleksandr Alekseev Emanuele Nevali Berkay Döner Omar El Malki Blagoj Mitrevski Leandro Kieliger Mark Collier Andrii Maksai Jesse Berent Claudiu Cristian Musat Efi Kokiopoulou Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation. ICCVW 2025 1893-1905 conf/iccv/2025w https://doi.org/10.1109/ICCVW69036.2025.00199 db/conf/iccv/iccv2025w.html#BrioschiANDMMKCMBMK25 streams/conf/iccv

Yiran Xu Siqi Xie Zhuofang Li Harris Shadmany Yinxiao Li Luciano Sbaiz Miaosen Wang Junjie Ke José Lezama Hang Qi Han Zhang 0010 Jesse Berent Ming-Hsuan Yang 0001 Irfan Essa Jiabin Huang 0001 Feng Yang 0008 HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations. 2025 April abs/2504.03026 CoRR https://doi.org/10.48550/arXiv.2504.03026 db/journals/corr/corr2504.html#abs-2504-03026 streams/journals/corr

Riccardo Brioschi Aleksandr Alekseev Emanuele Nevali Berkay Döner Omar El Malki Blagoj Mitrevski Leandro Kieliger Mark Collier Andrii Maksai Jesse Berent Claudiu Musat Efi Kokiopoulou Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation. 2025 October abs/2510.27632 CoRR https://doi.org/10.48550/arXiv.2510.27632 db/journals/corr/corr2510.html#abs-2510-27632 streams/journals/corr

Blagoj Mitrevski Arina Rak Julian Schnitzler Chengkun Li Andrii Maksai Jesse Berent Claudiu Musat InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write. 2024 abs/2402.05804 CoRR https://doi.org/10.48550/arXiv.2402.05804 db/journals/corr/corr2402.html#abs-2402-05804

Anastasiia Fadeeva Philippe Schlattner Andrii Maksai Mark Collier Efi Kokiopoulou Jesse Berent Claudiu Musat Representing Online Handwriting for Recognition in Large Vision-Language Models. 2024 abs/2402.15307 CoRR https://doi.org/10.48550/arXiv.2402.15307 db/journals/corr/corr2402.html#abs-2402-15307

Mesut Erhan Unal Keren Ye Mingda Zhang Christopher Thomas 0004 Adriana Kovashka Wei Li 0044 Danfeng Qin Jesse Berent Learning to Overcome Noise in Weak Caption Supervision for Object Detection. 4897-4914 2023 April 45 IEEE Trans. Pattern Anal. Mach. Intell. 4 https://doi.org/10.1109/TPAMI.2022.3187350 db/journals/pami/pami45.html#UnalYZTKLQB23

Mark Collier Rodolphe Jenatton Basil Mustafa Neil Houlsby Jesse Berent Effrosyni Kokiopoulou Massively Scaling Heteroscedastic Classifiers. 2023 ICLR https://openreview.net/forum?id=sIoED-yPK9l conf/iclr/2023 db/conf/iclr/iclr2023.html#CollierJMHBK23 Guillermo Ortiz-Jiménez Mark Collier Anant Nawalgaria Alexander Nicholas D'Amour Jesse Berent Rodolphe Jenatton Efi Kokiopoulou When does Privileged information Explain Away Label Noise? 26646-26669 2023 ICML https://proceedings.mlr.press/v202/ortiz-jimenez23a.html conf/icml/2023 db/conf/icml/icml2023.html#Ortiz-JimenezCN23 Jannik Kossen Mark Collier Basil Mustafa Xiao Wang 0038 Xiaohua Zhai Lucas Beyer Andreas Steiner 0001 Jesse Berent Rodolphe Jenatton Effrosyni Kokiopoulou Three Towers: Flexible Contrastive Learning with Pretrained Image Models. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/63d4316315900a62e610e5c17bab900a-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#KossenCMWZBSBJK23

Mark Collier Rodolphe Jenatton Basil Mustafa Neil Houlsby Jesse Berent Effrosyni Kokiopoulou Massively Scaling Heteroscedastic Classifiers. 2023 abs/2301.12860 CoRR https://doi.org/10.48550/arXiv.2301.12860 db/journals/corr/corr2301.html#abs-2301-12860

Guillermo Ortiz-Jiménez Mark Collier Anant Nawalgaria Alexander D'Amour Jesse Berent Rodolphe Jenatton Effrosyni Kokiopoulou When does Privileged Information Explain Away Label Noise? 2023 abs/2303.01806 CoRR https://doi.org/10.48550/arXiv.2303.01806 db/journals/corr/corr2303.html#abs-2303-01806

Jannik Kossen Mark Collier Basil Mustafa Xiao Wang 0038 Xiaohua Zhai Lucas Beyer Andreas Steiner 0001 Jesse Berent Rodolphe Jenatton Efi Kokiopoulou Three Towers: Flexible Contrastive Learning with Pretrained Image Models. 2023 abs/2305.16999 CoRR https://doi.org/10.48550/arXiv.2305.16999 db/journals/corr/corr2305.html#abs-2305-16999

Vincent Fortuin Mark Collier Florian Wenzel James Urquhart Allingham Jeremiah Zhe Liu Dustin Tran Balaji Lakshminarayanan Jesse Berent Rodolphe Jenatton Effrosyni Kokiopoulou Deep Classifiers with Label Noise Modeling and Distance Awareness. 2022 2022 Trans. Mach. Learn. Res. https://openreview.net/forum?id=Id7hTt78FV db/journals/tmlr/tmlr2022.html#FortuinCWALTLBJK22

Mark Collier Rodolphe Jenatton Effrosyni Kokiopoulou Jesse Berent Transfer and Marginalize: Explaining Away Label Noise with Privileged Information. 4219-4237 2022 ICML https://proceedings.mlr.press/v162/collier22a.html conf/icml/2022 db/conf/icml/icml2022.html#CollierJKB22

Mark Collier Rodolphe Jenatton Efi Kokiopoulou Jesse Berent Transfer and Marginalize: Explaining Away Label Noise with Privileged Information. 2022 abs/2202.09244 CoRR https://arxiv.org/abs/2202.09244 db/journals/corr/corr2202.html#abs-2202-09244

Andrii Maksai Henry A. Rowley Jesse Berent Claudiu Musat Inkorrect: Online Handwriting Spelling Correction. 2022 abs/2202.13794 CoRR https://arxiv.org/abs/2202.13794 db/journals/corr/corr2202.html#abs-2202-13794

Mark Collier Basil Mustafa Efi Kokiopoulou Rodolphe Jenatton Jesse Berent Correlated Input-Dependent Label Noise in Large-Scale Image Classification. 1551-1560 2021 CVPR https://openaccess.thecvf.com/content/CVPR2021/html/Collier_Correlated_Input-Dependent_Label_Noise_in_Large-Scale_Image_Classification_CVPR_2021_paper.html https://doi.org/10.1109/CVPR46437.2021.00160 conf/cvpr/2021 db/conf/cvpr/cvpr2021.html#CollierMKJB21

Mark Collier Basil Mustafa Efi Kokiopoulou Rodolphe Jenatton Jesse Berent Correlated Input-Dependent Label Noise in Large-Scale Image Classification. 2021 abs/2105.10305 CoRR https://arxiv.org/abs/2105.10305 db/journals/corr/corr2105.html#abs-2105-10305

Vincent Fortuin Mark Collier Florian Wenzel James Urquhart Allingham Jeremiah Z. Liu Dustin Tran Balaji Lakshminarayanan Jesse Berent Rodolphe Jenatton Effrosyni Kokiopoulou Deep Classifiers with Label Noise Modeling and Distance Awareness. 2021 abs/2110.02609 CoRR https://arxiv.org/abs/2110.02609 db/journals/corr/corr2110.html#abs-2110-02609

Efi Kokiopoulou Anja Hauth Luciano Sbaiz Andrea Gesmundo Gábor Bartók Jesse Berent Task-Aware Performance Prediction for Efficient Architecture Search. 1238-1245 2020 ECAI https://doi.org/10.3233/FAIA200224 conf/ecai/2020 db/conf/ecai/ecai2020.html#KokiopoulouHSGB20

Mark Collier Basil Mustafa Efi Kokiopoulou Jesse Berent Analysis of Softmax Approximation for Deep Classifiers under Input-Dependent Label Noise. 2020 abs/2003.06778 CoRR https://arxiv.org/abs/2003.06778 db/journals/corr/corr2003.html#abs-2003-06778

Mark Collier Efi Kokiopoulou Andrea Gesmundo Jesse Berent Routing Networks with Co-training for Continual Learning. 2020 abs/2009.04381 CoRR https://arxiv.org/abs/2009.04381 db/journals/corr/corr2009.html#abs-2009-04381

Keren Ye Mingda Zhang Adriana Kovashka Wei Li 0044 Danfeng Qin Jesse Berent Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection. 9685-9694 2019 ICCV https://doi.org/10.1109/ICCV.2019.00978 conf/iccv/2019 db/conf/iccv/iccv2019.html#YeZKLQB19

Efi Kokiopoulou Anja Hauth Luciano Sbaiz Andrea Gesmundo Gábor Bartók Jesse Berent Fast Task-Aware Architecture Inference. 2019 abs/1902.05781 CoRR http://arxiv.org/abs/1902.05781 db/journals/corr/corr1902.html#abs-1902-05781

Keren Ye Mingda Zhang Adriana Kovashka Wei Li 0044 Danfeng Qin Jesse Berent Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection. 2019 abs/1907.10164 CoRR http://arxiv.org/abs/1907.10164 db/journals/corr/corr1907.html#abs-1907-10164

Krzysztof Maziarz Efi Kokiopoulou Andrea Gesmundo Luciano Sbaiz Gábor Bartók Jesse Berent Gumbel-Matrix Routing for Flexible Multi-task Learning. 2019 abs/1910.04915 CoRR http://arxiv.org/abs/1910.04915 db/journals/corr/corr1910.html#abs-1910-04915

Alina Dubatovka Efi Kokiopoulou Luciano Sbaiz Andrea Gesmundo Gábor Bartók Jesse Berent Ranking architectures using meta-learning. 2019 abs/1911.11481 CoRR http://arxiv.org/abs/1911.11481 db/journals/corr/corr1911.html#abs-1911-11481

Keren Ye Mingda Zhang Wei Li 0044 Danfeng Qin Adriana Kovashka Jesse Berent Learning to discover and localize visual objects with open vocabulary. 2018 abs/1811.10080 CoRR http://arxiv.org/abs/1811.10080 db/journals/corr/corr1811.html#abs-1811-10080

Wen Li 0001 Limin Wang 0002 Wei Li 0044 Eirikur Agustsson Jesse Berent Abhinav Gupta 0001 Rahul Sukthankar Luc Van Gool WebVision Challenge: Visual Learning and Understanding With Web Data. 2017 abs/1705.05640 CoRR http://arxiv.org/abs/1705.05640 db/journals/corr/corr1705.html#LiWLABGSG17

Andriy Gelman Jesse Berent Pier Luigi Dragotti Layer-based sparse representation of multiview images. 61 2012 2012 EURASIP J. Adv. Signal Process. https://doi.org/10.1186/1687-6180-2012-61 https://www.wikidata.org/entity/Q59291510 db/journals/ejasp/ejasp2012.html#GelmanBD12

Jesse Berent Pier Luigi Dragotti Thierry Blu Sampling piecewise sinusoidal signals with finite rate of innovation methods. 613-625 2010 58 IEEE Trans. Signal Process. 2 https://doi.org/10.1109/TSP.2009.2031717 db/journals/tsp/tsp58.html#BerentDB10

Jesse Berent Pier Luigi Dragotti Mike Brookes Adaptive layer extraction for image based rendering. 1-6 2009 MMSP https://doi.org/10.1109/MMSP.2009.5293298 conf/mmsp/2009 db/conf/mmsp/mmsp2009.html#BerentDB09

Jesse Berent Pier Luigi Dragotti Plenoptic Manifolds. 34-44 2007 24 IEEE Signal Process. Mag. 6 https://doi.org/10.1109/MSP.2007.905883 db/journals/spm/spm24.html#BerentD07

Jesse Berent Pier Luigi Dragotti Unsupervised Extraction of Coherent Regions for Image Based Rendering. 2007 BMVC https://doi.org/10.5244/C.21.28 conf/bmvc/2007 db/conf/bmvc/bmvc2007.html#BerentD07 1-10 Jesse Berent Pier Luigi Dragotti Perfect Reconstruction Schemes for Sampling Piecewise Sinusoidal Signals. 377-380 2006 ICASSP (3) https://doi.org/10.1109/ICASSP.2006.1660669 conf/icassp/2006 db/conf/icassp/icassp2006.html#BerentD06 Jesse Berent Pier Luigi Dragotti Segmentation of Epipolar-Plane Image Volumes with Occlusion and Disocclusion Competition. 182-185 2006 MMSP https://doi.org/10.1109/MMSP.2006.285293 conf/mmsp/2006 db/conf/mmsp/mmsp2006.html#BerentD06 Brigitte Forster Dimitri Van De Ville Jesse Berent Daniel Sage Michael Unser Extended Depth-of-Focus for Multi-Channel Microscopy Images: A Complex Wavelet Approach. 660-663 2004 conf/isbi/2004 ISBI db/conf/isbi/isbi2004.html#ForsterVBSU04 https://doi.org/10.1109/ISBI.2004.1398624 Eirikur Agustsson Aleksandr Alekseev James Urquhart Allingham Gábor Bartók Lucas Beyer Thierry Blu Riccardo Brioschi Mike Brookes Mark Collier Alexander D'AmourAlexander Nicholas D'Amour Berkay Döner Pier Luigi Dragotti Alina Dubatovka Irfan A. EssaIrfan Essa Anastasiia Fadeeva Brigitte Forster-HeinleinBrigitte Forster Vincent Fortuin Andriy Gelman Andrea Gesmundo Luc Van Gool Abhinav Gupta 0001 Anja Hauth Neil Houlsby Jia-Bin Huang 0001Jiabin Huang 0001 Rodolphe Jenatton Junjie Ke Leandro Kieliger Effrosyni KokiopoulouEfi Kokiopoulou Jannik Kossen Adriana Kovashka Balaji Lakshminarayanan José Lezama Chengkun Li Wei Li 0044 Wen Li 0001 Yinxiao Li Zhuofang Li Jeremiah Z. LiuJeremiah Zhe Liu Andrii Maksai Omar El Malki Krzysztof Maziarz Blagoj Mitrevski Claudiu Cristian MusatClaudiu Musat Basil Mustafa Anant Nawalgaria Emanuele Nevali Guillermo Ortiz-Jiménez Hang Qi Danfeng Qin Arina Rak Henry A. Rowley Daniel Sage Luciano Sbaiz Philippe Schlattner Julian Schnitzler Harris Shadmany Andreas Steiner 0001 Rahul Sukthankar Christopher Thomas 0004 Dustin Tran Mesut Erhan Unal Michael Unser Dimitri Van De Ville Limin Wang 0002 Miaosen Wang Xiao Wang 0038 Florian Wenzel Siqi Xie Yiran Xu Feng Yang 0008 Ming-Hsuan Yang 0001 Keren Ye Xiaohua Zhai Han Zhang 0010 Mingda Zhang